SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3011–3020 of 3569 papers

TitleStatusHype
Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error—0
Learning Context-aware Task Reasoning for Efficient Meta-reinforcement Learning—0
Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning—0
Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?—0
Using a thousand optimization tasks to learn hyperparameter search strategies—0
Adversarial Monte Carlo Meta-Learning of Optimal Prediction ProceduresCode0
Provable Meta-Learning of Linear RepresentationsCode0
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning—0
KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification—0
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning—0
Show:102550
← PrevPage 302 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified